搜索结果: 61-75 共查到“知识库 词汇学”相关记录505条 . 查询时间(1.39 秒)
Generalization with Componential Attractors:Word and Nonword Reading in an Attractor Network
Generalization with Componential Attractors Word and Nonword Reading Attractor Network
2015/6/19
Networks that learn to make familiar activity patterns into stable attractors have proven useful in accounting for many aspects of normal and impaired cognition. However, their ability to generalize i...
More Words but Still No Lexicon: Reply to Besner et al. (1990)
Still No Lexicon Reply to Besner
2015/6/19
The major points in the Besner, Twilley, McCann, and Seergobin (1990) critique of the Seidenberg and McClelland (1989) model are addressed. The model's performancediffers from that of people in ways t...
The role of familiar units in perception of words and nonwords
familiar units perception of words nonwords
2015/6/19
The role of familiar units in perception of words and nonwords.
A lexical transducer, first discussed in Karttunen, Kaplan and Zaenen 1992, is a specialised finite-state automaton that maps inflected surface forms to lexical forms, and vice versa. The lexical form...
The notion of exception presupposes that of rule; as Webster puts it, an exception is “a
case to which a rule does not apply”. Linguistic rules (and, more recently, constraints,
principles, paramete...
While these are general questions that cannot be fully approached let
alone answered here, they are important nevertheless as their terms betray
that transitional justice is a relatively new and u...
Natural uses of dative constructions in English reveal that the boundaries between categoricity and gradience are fluid in both lexicon and grammar.1 In the lexicon, the mapping between semantic class...
Retained inflectional morphology in pidgins:A typological study
diachrony inflectional morphology language contact markedness pidgins
2015/6/17
It is commonly accepted that the process of pidginization leads to a loss of inflectional morphology, but this loss is often not total. Lexifier inflections instead follow a cline of reduction: full r...
Grammatical theory has long wrestled with the fact that causative constructions exhibit properties of both single words and complex phrases. However, as Paul Kiparsky has observed, the distribution of...
What’s needed for lexical databases?Experiences with Kirrkirr
lexical databases Experiences Kirrkirr
2015/6/12
This paper discusses what is required from dictionary databases, and one approach, based on experience with Kirrkirr, a dictionary browser originally developed for Warlpiri, an Indigenous Australian l...
Which words are hard to recognize?Prosodic,lexical,and disfluency factors that increase ASR error rates
Which words are hard to recognize Prosodic lexical disfluency factors increase ASR error rates
2015/6/12
Many factors are thought to increase the chances of misrecognizing a word in ASR, including low frequency, nearby disfluencies, short duration, and being at the start of a turn. However, few of these ...
Natural language understanding depends heavily on assessing veridicality – whether the speaker intends to convey that events mentioned are actual, non-actual, or uncertain. However, this property is l...
Embedded implicatures as pragmatic inferences under compositional lexical uncertainty
Embedded implicatures compositional lexical uncertainty
2015/6/11
How do comprehenders reason about pragmatically ambiguous scalar terms like some in
complex syntactic contexts? In many pragmatic theories of conversational implicature, local
exhaustification...
Parsing Time:Learning to Interpret Time Expressions
Parsing Time Interpret Time Expressions
2015/6/10
We present a probabilistic approach for learning to interpret temporal phrases given only a corpus of utterances and the times they reference. While most approaches to the task have used regular expre...
Generating Recommendation Dialogs by Extracting Information from User Reviews
Generating Recommendation Dialogs Extracting Information User Reviews
2015/6/10
Recommendation dialog systems help users navigate e-commerce listings by asking questions about users’ preferences toward relevant domain attributes. We present a framework for generating and ranking ...